Device for automatic sensing of made and missed sporting attempts
A basketball shot counter includes a mounting shaped and sized to connect the basketball shot counter to a portion of a basketball goal having a basketball hoop; a vibration sensor; a processor in data communication with the vibration sensor, wherein the processor is configured to receive, from the vibration sensor, a datastream of vibration sensor readings; determine, from the datastream of vibration sensor readings, that a first basketball shot was attempted without successfully going through the basketball hoop; and determine, from the datastream of vibration sensor readings, that a second basketball shot was attempted and successfully went through the basketball hoop.
1. A basketball shot counter system comprising:
a mounting shaped and sized to connect the basketball shot counter system to a portion of a basketball goal having a basketball hoop;
a vibration sensor; and
a processor in data communication with the vibration sensor, wherein the processor is configured to:
receive, from the vibration sensor, a datastream of vibration sensor readings;
determine, from the datastream of vibration sensor readings, that a first basketball shot was attempted without successfully going through the basketball hoop;
determine, from the datastream of vibration sensor readings, that a second basketball shot was attempted and successfully went through the basketball hoop; and
responsive to the determination that the second basketball shot was attempted and successfully went through the basketball hoop, transmit to a client device a made-message indicating that the second basketball shot was attempted and successfully went through the basketball hoop,
wherein, to determine, based on a set of recent sensor readings, that the second basketball shot was attempted and successfully went through the basketball hoop, the processor is configured to:
submit the set of recent sensor readings to a made-classifier;
receive, from the made-classifier, a made-confidence that measures a likelihood that the set of recent sensor readings correspond to a made basketball shot; and
compare the made-confidence against a made-threshold value that indicates a minimum likelihood for the second basketball shot to be considered made.
2. The basketball shot counter system of claim 1 , wherein the processor is configured to distinguish vibration sensor readings indicative of a made shot from vibration sensor readings indicative of a missed shot.
3. The basketball shot counter system of claim 1 , wherein the processor is configured to distinguish vibration sensor readings indicative of a made shot from vibration sensor readings indicative of a missed shot based on a predictive model that is configured to predict whether a shot is made based upon one or more machine-learning trained classifiers and the datastream of vibration sensor readings.
4. The basketball shot counter system of claim 1 , wherein the vibration sensor comprises an accelerometer, and wherein the basketball shot counter system further comprises a magnetometer and a gyroscope.
5. The basketball shot counter of system claim 1 , wherein the datastream comprises a first set of vibration data and a second set of vibration data, wherein the processor is configured to interpret the first set of vibration data as being indicative of a missed shot when the first set of vibration data appears without the second set of vibration data and the processor is configured to interpret the first set of vibration data as being indicative of a made shot when the first set of vibration data appears with the second set of vibration data.
6. The basketball shot counter system of claim 1 , wherein the basketball shot counter system comprises an impact member in vibrational communication with the vibration sensor, wherein the impact member is sized and configured to be positioned in a ball path under the basketball hoop when the basketball shot counter system is mounted to the basketball goal.
7. The basketball shot counter system of claim 1 , wherein the basketball goal further comprises a backboard and a net, and wherein the basketball shot counter system is configured to transfer vibration from the basketball goal to the vibration sensor when a basketball impacts the backboard and when the basketball impacts the basketball hoop.
8. The basketball shot counter system of claim 1 , wherein a single unit comprises the mounting, the vibration sensor, and the processor.
9. The basketball shot counter system of claim 1 , wherein the processor is physically remote from the vibration sensor and the mounting and wherein the processor is a part of a client device.
10. A sports shot counter comprising:
a mounting shaped and sized to connect the sports shot counter to a portion of a sports goal;
a sensor configured to sense an impact; and
a processor in data communication with the sensor, wherein the processor is configured to sense and distinguish between made shots and missed shots as a function of sensed impact,
wherein the sensor is a vibration sensor configured to sense impact with the sports goal and wherein the processor is configured to sense and distinguish between made shots and missed shots as a function vibration caused by impact with the sports goal, and
wherein, to submit a set of recent sensor readings to a made-classifier, the processor is configured to:
generate, from the set of recent sensor readings, a maximal feature that represents a maximal measure of the vibrations; and
generate, from the set of recent sensor readings, an aggregate feature that represents an aggregate measure of the vibrations.
11. The sports shot counter of claim 10 , wherein the processor distinguishes between made shots and missed shots according to a predictive model of trained classifiers.
12. A device for determining made-attempts in a sporting activity, the device comprising:
a primary housing;
a vibration sensor mechanically coupled to the primary housing and configured to sense vibrations of the primary housing;
an impact member in vibrational communication with the primary housing, the impact member comprising a metal spring in a curved tube;
a mounting shaped to interface with a goal usable for the sporting activity in order to attach the device to the goal; and
a processor configured to:
receive, from the vibration sensor, a datastream of sensor readings;
identify a set of recent sensor readings;
determine, based on the set of recent sensor readings, if an attempt of the sporting activity was made; and
responsive to the determination, transmit to a client device a made-message indicating if the attempt of the sporting activity was made,
wherein, to determine, based on the set of recent sensor readings, if the attempt of the sporting activity was made, the processor is configured to:
submit the set of recent sensor readings to a made-classifier;
receive, from the made-classifier, a made-confidence that measures a likelihood that the set of recent sensor readings correspond to a made attempt of the sporting activity; and
compare the made-confidence against a made-threshold value that indicates a minimum likelihood for the attempt of the sporting activity to be considered made.
13. The device of claim 12 , wherein impact by a basketball with the impact member creates first vibrations in the impact member, and wherein the first vibrations are communicated from the impact member to the primary housing sensed by the vibration sensor.
14. The device of claim 12 , wherein impact by a basketball with a basketball hoop that is connected to the primary housing creates second vibrations of the primary housing sensed by the vibration sensor.
15. The device of claim 14 , wherein the processor is configured to determine if the attempt of the sporting activity was made based at least in part on the second vibrations.
16. The device of claim 15 , wherein the attempt of the sporting activity was made.
17. The device of claim 16 , wherein the attempt of the sporting activity was not made.
18. The sports shot counter of claim 10 , wherein the maximal feature is a largest change in acceleration in sequential sensor readings in the set of recent sensor readings; and wherein the aggregate feature is a summation of every change in acceleration in sequential sensor readings in the set of recent sensor readings.
19. The sports shot counter of claim 10 , wherein:
the vibration sensor is an accelerometer that is configured to sense acceleration in an X-direction, acceleration in a Y-direction, and acceleration in a Z-direction; and
each sensor reading in the datastream of sensor readings comprises an X-value corresponding to the sensed acceleration in the X-direction, a Y-value corresponding to the sensed acceleration in the Y-direction, and a Z-value corresponding to the sensed acceleration in the Z-direction.
20. The device of claim 12 wherein, to submit the set of recent sensor readings to a made-classifier, the processor is configured to:
generate, from the set of recent sensor readings, a maximal feature that represents a maximal measure of the vibrations; and
generate, from the set of recent sensor readings, an aggregate feature that represents an aggregate measure of the vibrations.
21. The device of claim 20 , wherein the maximal feature is a largest change in acceleration in sequential sensor readings in the set of recent sensor readings; and wherein the aggregate feature is a summation of every change in acceleration in sequential sensor readings in the set of recent sensor readings.
22. The device of claim 20 , wherein:
the vibration sensor is an accelerometer that is configured to sense acceleration in an X-direction, acceleration in a Y-direction, and acceleration in a Z-direction; and
each sensor reading in the datastream of sensor readings comprises an X-value corresponding to the sensed acceleration in the X-direction, a Y-value corresponding to the sensed acceleration in the Y-direction, and a Z-value corresponding to the sensed acceleration in the Z-direction.